Lai Shuo-Lun, Chen Chi-Sheng, Lin Been-Ren, Chang Ruey-Feng
Graduate Institute of Biomedical Electronics and Bioinformatics, National Taiwan University, No.1, Sec.4, Roosevelt Road, Taipei, 10617, Taiwan.
Division of Colorectal Surgery, Department of Surgery, National Taiwan University Hospital and National Taiwan University College of Medicine, Taipei, Taiwan.
Ann Biomed Eng. 2023 Feb;51(2):352-362. doi: 10.1007/s10439-022-03033-9. Epub 2022 Aug 16.
During laparoscopic surgery, surgical gauze is usually inserted into the body cavity to help achieve hemostasis. Retention of surgical gauze in the body cavity may necessitate reoperation and increase surgical risk. Using deep learning technology, this study aimed to propose a neural network model for gauze detection from the surgical video to record the presence of the gauze. The model was trained by the training group using YOLO (You Only Look Once)v5x6, then applied to the testing group. Positive predicted value (PPV), sensitivity, and mean average precision (mAP) were calculated. Furthermore, a timeline of gauze presence in the video was drawn by the model as well as human annotation to evaluate the accuracy. After the model was well-trained, the PPV, sensitivity, and mAP in the testing group were 0.920, 0.828, and 0.881, respectively. The inference time was 11.3 ms per image. The average accuracy of the model adding a marking and filtering process was 0.899. In conclusion, surgical gauze can be successfully detected using deep learning in the surgical video. Our model provided a fast detection of surgical gauze, allowing further real-time gauze tracing in laparoscopic surgery that may help surgeons recall the location of the missing gauze.
在腹腔镜手术中，通常会将手术纱布插入体腔以帮助实现止血。手术纱布留在体腔内可能需要再次手术并增加手术风险。本研究利用深度学习技术，旨在提出一种用于从手术视频中检测纱布的神经网络模型，以记录纱布的存在情况。该模型由训练组使用YOLO（You Only Look Once）v5x6进行训练，然后应用于测试组。计算阳性预测值（PPV）、灵敏度和平均精度均值（mAP）。此外，该模型以及人工标注绘制了视频中纱布存在的时间线，以评估准确性。模型训练良好后，测试组中的PPV、灵敏度和mAP分别为0.920、0.828和0.881。推理时间为每张图像11.3毫秒。添加标记和过滤过程后的模型平均准确率为0.899。总之，利用深度学习可在手术视频中成功检测出手术纱布。我们的模型能够快速检测手术纱布，从而在腹腔镜手术中实现进一步的实时纱布追踪，这可能有助于外科医生找回丢失纱布的位置。
